FB openclaw-nextcloud
Manage Notes, Tasks, Calendar, Files, Contacts, and Deck Kanban boards in your Nextcloud instance via CalDAV, WebDAV, Notes, and Deck APIs. Use for creating notes, managing todos and calendar events, uploading/downloading files, managing contacts, and organizing Kanban boards, stacks, and cards.
As a process B 76/100 · Nearly there — weak spots: running it twice, progress reporting
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".
If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
How to improve
- Remove the critical guard findings (secrets, dangerous commands, hidden instructions): while they stand the skill is blocked and cannot grade above F.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 6
-
critical Exfiltration
exfil-send-secrets-to-urlindex.js:60Instruction to send secrets/history to an external endpoint (quoted — discussed, not commanded)message: `Refusing to send credentials over '${parsed.protocol}//' to '${parsed.host}'. Use https:// or set OPENCLAW_ALLOW_HTTP=1 to override (not recommended).`quoted
Medium and low: 5
-
medium Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: Bashallowed-tools: Bash Read
-
low Secrets in code
secret-high-entropy-tokenpackage-lock.json:84High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)"integrity": "sha5…S4F+im88…HRE/cYlx…2oE/ufM0p61IKng==",
detector -
low Secrets in code
secret-high-entropy-tokenpackage-lock.json:135High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)"integrity": "sha5…rdY+ziCYCPMmtZjjIwOmXFjmyzEHn+UUxk5of+SYsj…5hY/rOAw==",
detector -
low Secrets in code
secret-high-entropy-tokenpackage-lock.json:220High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)"integrity": "sha5…NmN+loZK…eAz+famM…vZz+zT1jlh/keC3Rj/lg==",
detector -
low Secrets in code
secret-high-entropy-tokenpackage-lock.json:623High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)"integrity": "sha5…SN2+yCV/fTW3…TGk+dvvn…Mwg==",
detector
Files scanned: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5272 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 76/100
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 101 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Failures and branches. 10 branches
- 70Execution cost. Instruction body is 5272 tokens
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 135 steps
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 11 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (28 tags): a typed call is more reliable
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- -226 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 296: enough signal without eating the budget
- +4Structure: 49 headings
- +3Step-by-step instructions: 135 items
- +3Output format is stated explicitly
- +4Has examples (14 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.